1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
|
#!/bin/sh
set -eu
usage() {
cat <<-'EOF'
Usage:
genhtml.sh FILENAME
genhtml.sh -h
EOF
}
help() {
cat <<-'EOF'
Options:
-h, --help show this message
FILENAME the name of the input file, to also be used as
URL
Process the FILENAME, and generate a full HTML page.
The FILENAME is used to infer the output URL, by removing the
`src/content/` prefix, and replacing the trailing `.md` with
`.html`. This URL is used to build the self-referencing
"canonical" link, extracting plaintext snippets, etc.
Examples:
Generate the HTML for a pastebin:
$ sh genhtml.sh src/content/a-paste.md > src/content/a-paste.html
EOF
}
for f in "$@"; do
case "$f" in
--)
break
;;
--help)
usage
help
exit
;;
*)
;;
esac
done
while getopts 'h' flag; do
case "$flag" in
h)
usage
help
exit
;;
*)
usage >&2
exit 2
;;
esac
done
shift $((OPTIND - 1))
. src/development/lib.sh
FILENAME="${1:-}"
eval "$(assert_arg "$FILENAME" 'FILENAME')"
# shellcheck source=/dev/null
. "${FILENAME%.md}.conf"
#
# Utility functions
#
SEEN_SLUGS="$(mkstemp)"
slugify_once() {
SLUG="$(printf '%s' "$1" | slugify)${2:+-$2}"
if grep -q "^$SLUG$" "$SEEN_SLUGS"; then
N="${2:-0}"
N=$((N + 1))
slugify_once "$1" "$N"
else
printf '%s\n' "$SLUG" >> "$SEEN_SLUGS"
printf '%s' "$SLUG"
fi
}
markdown_to_html() {
md2html
}
extract_plaintext_snippets() {
F="$(mkstemp)"
cat > "$F"
(
IFS=''
BLOCK_NUMBER=0
IN_BLOCK=
while read -r line; do
if [ "$line" = '</code></pre>' ]; then
IN_BLOCK=
fi
if [ -n "$IN_BLOCK" ]; then
printf '%s\n' "$line" | htmlesc -d >> "$OUT"
fi
if printf '%s' "$line" | grep -q '^<pre><code.*>'; then
IN_BLOCK=1
OUT="${FILENAME%.md}.html.$BLOCK_NUMBER.txt"
BLOCK_NUMBER=$((BLOCK_NUMBER + 1))
printf '%s\n' "$line" |
sed 's|^\(<pre><code.*>\)\(.*\)$|\2|' |
htmlesc -d > "$OUT"
fi
done < "$F"
BLOCK_NUMBER=0
while read -r line; do
printf '%s\n' "$line"
if [ "$line" = '</code></pre>' ]; then
printf '<p class="plaintext-link"><a href="%s.%s.txt">plaintext</a></p>\n' "$(url-for "$URL")" "$BLOCK_NUMBER"
BLOCK_NUMBER=$((BLOCK_NUMBER + 1))
fi
done < "$F"
)
}
add_line_numbers() {
awk '
/^<\/code><\/pre>$/ {
in_block = 0
printf "</tbody></table>%s\n", $0
next
}
match($0, /^(<pre><code.*>)(.*)$/, a) {
printf "%s<table rules=columns class=\"code-block\"><tbody>", a[1]
n = 1
block_count++
printf "<tr><td class=\"line-number\"><a id=\"B%s-L%s\" href=\"#B%s-L%s\">%s</a></td><td class=\"code-line\">%s</td></tr>\n", block_count, n, block_count, n, n, a[2]
in_block = 1
next
}
in_block == 1 {
n++
printf "<tr><td class=\"line-number\"><a id=\"B%s-L%s\" href=\"#B%s-L%s\">%s</a></td><td class=\"code-line\">%s</td></tr>\n", block_count, n, block_count, n, n, $0
next
}
{ print }
'
}
add_headings_anchors() {
(
IFS=''
while read -r line; do
if ! printf '%s' "$line" | grep -q '^<h[2-6]>'; then
printf '%s\n' "$line"
continue
fi
LVL="$(printf '%s' "$line" | sed 's|^<h\(.\)>.*|\1|')"
HEADING="$(printf '%s' "$line" | sed 's|^<h.>\(.*\)</h.>$|\1|')"
SLUG="$(slugify_once "$HEADING")"
printf '<h%s class="header-anchor" id="%s">%s<a href="#%s" aria-hidden="true"><img class="svg-icon" src="%s" /></a></h%s>\n' \
"$LVL" \
"$SLUG" \
"$HEADING" \
"$SLUG" \
"$(url-for 'static/link.svg')" \
"$LVL"
done
)
}
emit_body() {
< "${FILENAME%.md}.content" \
markdown_to_html |
extract_plaintext_snippets |
add_line_numbers |
add_headings_anchors
}
envsubst < src/lib/preamble.html
envsubst < src/lib/postamble.html
|
